Zhaoyi Liu
Papers
1
Total Citations
7
H-Index
1
About
Zhaoyi Liu is a researcher advancing the field of acoustic signal processing, with a primary focus on speech enhancement using innovative sensor technologies. His key research areas include multichannel signal processing, acoustic vector sensor (AVS) applications, and nonlinear masking techniques for target speech extraction. Liu’s major contribution lies in developing a nonlinear soft masking approach that leverages the inter-sensor data ratio (ISDR) model from a single acoustic vector sensor to enhance target speech captured by distant microphones. This work, published in 2018, has garnered 7 citations and addresses the persistent challenge of improving speech intelligibility in noisy, real-world environments. By exploiting the unique time-frequency domain properties of AVS, Liu’s method offers a more robust alternative to traditional beamforming, enabling clearer speech extraction with minimal hardware. His research holds promise for applications in hearing aids, smart devices, and surveillance systems, where distant microphone capture is common. Liu’s contributions demonstrate a keen ability to bridge theoretical signal models with practical audio enhancement solutions, marking him as a thoughtful innovator in acoustic engineering.
Research Focus
Key Achievements
Top Papers
- 1